dhh-rails-style
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill consists entirely of markdown documentation providing stylistic guidance for Ruby on Rails development. It does not contain any executable logic or scripts.
- [DATA_EXPOSURE] (SAFE): No hardcoded credentials, API keys, or sensitive file paths were found across the main file or the four reference files. The documentation adheres to best practices.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not contain any commands to download or execute external scripts. While it mentions gems and libraries (e.g., Kamal, Solid Queue, and Bcrypt), these are provided as architectural context for code generation rather than instructions for immediate installation or execution by the agent.
- [COMMAND_EXECUTION] (SAFE): No shell commands, subprocess calls, or privileged operations (like sudo) are included in the instructions. The skill is purely text-based instructions for the LLM.
- [PROMPT_INJECTION] (SAFE): The instructions are focused on a specific coding persona (DHH/37signals style) and do not attempt to override the AI agent's core safety instructions, bypass filters, or extract system prompts.
Audit Metadata